pytorch实现CNN网络---mnist实例

 

CNN网络代码实现，使用LeNet-5,详情参考文章 网络解析（一）：LeNet-5详解

cnn.py

from torch import nn

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, kernel_size=5, padding=2)
        self.conv2 = nn.Conv2d(6, 16, kernel_size=5)
        self.conv3 = nn.Conv2d(16, 120, kernel_size=5)
        self.mp = nn.MaxPool2d(2)
        self.relu = nn.ReLU()
        self.fc1 = nn.Linear(120, 84)
        self.fc2 = nn.Linear(84, 10)
        self.logsoftmax = nn.LogSoftmax()

    def forward(self, x):
        in_size = x.size(0)
        out = self.relu(self.mp(self.conv1(x)))
        out = self.relu(self.mp(self.conv2(out)))
        out = self.relu(self.conv3(out))
        out = out.view(in_size, -1)
        out = self.relu(self.fc1(out))
        out = self.fc2(out)
        return self.logsoftmax(out)

训练代码实现：

import torch
from torch import nn, optim
from torch.autograd import Variable
from torch.utils.data import DataLoader
from torchvision import datasets, transforms

import cnn

# 定义一些超参数
batch_size = 64
learning_rate = 0.02
num_epoches = 20

# 数据预处理。transforms.ToTensor()将图片转换成PyTorch中处理的对象Tensor,并且进行标准化（数据在0~1之间）
# transforms.Normalize()做归一化。它进行了减均值，再除以标准差。两个参数分别是均值和标准差
# transforms.Compose()函数则是将各种预处理的操作组合到了一起
data_tf = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize([0.5], [0.5])])

# 数据集的下载器
train_dataset = datasets.MNIST(
    root='./data', train=True, transform=data_tf, download=True)
test_dataset = datasets.MNIST(root='./data', train=False, transform=data_tf)
# 迭代器
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

# 选择模型
model = cnn.CNN()
if torch.cuda.is_available():
    model = model.cuda()

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=learning_rate)

# 训练模型
epoch = 0
for data in train_loader:
    img, label = data
    # img = img.view(img.size(0), -1)
    img = Variable(img)
    if torch.cuda.is_available():
        img = img.cuda()
        label = label.cuda()
    else:
        img = Variable(img)
        label = Variable(label)

    out = model(img)
    loss = criterion(out, label)
    print_loss = loss.data.item()

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    epoch+=1
    if epoch%50 == 0:
        print('epoch: {}, loss: {:.4}'.format(epoch, loss.data.item()))

# 模型评估
model.eval()
eval_loss = 0
eval_acc = 0
for data in test_loader:
    img, label = data
    # img = img.view(img.size(0), -1)
    img = Variable(img)
    if torch.cuda.is_available():
        img = img.cuda()
        label = label.cuda()

    out = model(img)
    loss = criterion(out, label)
    eval_loss += loss.data.item()*label.size(0)
    _, pred = torch.max(out, 1)
    num_correct = (pred == label).sum()
    eval_acc += num_correct.item()
print('Test Loss: {:.6f}, Acc: {:.6f}'.format(
    eval_loss / (len(test_dataset)),
    eval_acc / (len(test_dataset))
))

结果：

 

代码参考：PyTorch基础入门六：PyTorch搭建卷积神经网络实现MNIST手写数字识别

CNN简单理解+PyTorch示例实现

一文搞定Pytorch+CNN讲解

pytorch基础入门教程/一小时学会pytorch